© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24288
    Prev
    Next
    INDEX
    Explanations

    phrases related to various global locations

    oai_token-act-pair · gpt-3.5-turbo

    high-impact nouns and titles related to events and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )).
    -0.28
    }.
    -0.25
     respectively
    -0.25
    )))
    -0.24
    é¾įå¥ij士
    -0.23
    ).[
    -0.23
    %).
    -0.22
    .).
    -0.22
    èĢ
    -0.22
     latter
    -0.21
    POSITIVE LOGITS
     Pastebin
    0.25
    epad
    0.25
    =-=-
    0.24
    earchers
    0.23
    iple
    0.23
     glim
    0.22
    izon
    0.22
     href
    0.21
    ascar
    0.21
     depends
    0.20
    Activations Density 11.263%

    No Known Activations